Page 79 - Undergraduate Research Opportunities Program Proceedings 2017-18

School of Engineering
Department of Computer Science & Engineering

corresponding object changes during this interval. HKUST is a technological university accommodating over 10000
students and staff who busily cross through various zones. Therefore, as for our project, we choose people in HKUST to
see how they move around in the university every day. How people’s locations vary with time and which approach they
select interest us a lot. After studying it, we develop a visual web page to demonstrate these contents and draw some
conclusions about people’s daily lifestyle in HKUST. In a long run, this system can undoubtedly be applied to more
general cases and the result will be more influential.

Supervisor: QU Huamin / CSE
Student: DU Wei / COMP Course: UROP1100, Summer
JIANG Kuo / SENG UROP1100, Summer
SHUM Ka Chun / SENG UROP1100, Summer

In order to better understand a university, watching its campus news is one of the best way. However, simply going to
the campus news website to watch news is absolutely not convenient enough because it is time-consuming for a person
to read all the news articles that are published in different time. And it is also difficult for us to take a full look on one
specific aspect of a university. Our project is mainly aim at the people who want to have a quick and holistic
understanding of HKUST. By using Python and Javascript for data crawling and data processing, using HTML and d3
methods for visualization, the goal of our system is to provide a webpage with a chart that shows visualized information
for users. In the report, we will describe how we find a way to define the similarity of the news and how we finish
establishing the project step by step.

Supervisor: QU Huamin / CSE
Student: LI Xiang / SENG Course: UROP1100, Summer
SONG Sizhe / SENG UROP1000, Summer
SUN Yushi / SENG UROP1000, Summer

With the population in the campus rising over time and the cease of coffee shop’s catering service, most students have
undergone exceeding crowdedness in campus canteens, which wasted our time and brought much inconvenience. If
there’s a program to process the historical population data of canteens and visualize them in a user-friendly manner, the
problem is likely to be solved. It may also help students to avoid rush hours so that they won’t waste too much time in a
long queue. In this report, we will introduce our work, an HKUST canteen population data visualization tool and how we
have designed and developed it.

Supervisor: QU Huamin / CSE
Student: WANG Yanbang / COSC Course: UROP3100, Spring

Recent development in techniques has made possible emotion recognition in video streams. However, the newly
available information has not been effectively leveraged to provide extra insight in terms of video analysis. This report
summarizes my work over the process of participating in research paper writing: Emotion-Oriented Visual
Summarization of Classroom Videos. It outlines the working pipeline, and provides clarification and reflection on top of
the original paper.

Supervisor: QU Huamin / CSE
Student: FANG Juanru / COMP Course: UROP1100, Summer
XIAO Tianyi / COMP UROP1100, Summer

69